Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 774 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1208. Min Range: -8.1208
Max Act: 8.1208. Min Act: -0.1700
Data Index: 7772725 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.6520. Min Act: -0.1700
Data Index: 5155966 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.5583. Min Act: -0.1700
Data Index: 7479947 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.5583. Min Act: -0.1700
Data Index: 4590973 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.4333. Min Act: -0.1700
Data Index: 8800583 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.4020. Min Act: -0.1700
Data Index: 1823915 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.3708. Min Act: -0.1700
Data Index: 5850945 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.3083. Min Act: -0.1700
Data Index: 3018246 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.3083. Min Act: -0.1700
Data Index: 7844902 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.2458. Min Act: -0.1700
Data Index: 3075786 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.1833. Min Act: -0.1700
Data Index: 5838062 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.1833. Min Act: -0.1700
Data Index: 6873793 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.1208. Min Act: -0.1700
Data Index: 2787003 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.0583. Min Act: -0.1700
Data Index: 3603120 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.0270. Min Act: -0.1700
Data Index: 6803442 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1208. Min Range: -8.1208
Max Act: 7.0270. Min Act: -0.1700
Data Index: 2929651 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1208. Min Range: -8.1208
Max Act: 6.9958. Min Act: -0.1700
Data Index: 315778 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1208. Min Range: -8.1208
Max Act: 6.9958. Min Act: -0.1700
Data Index: 8742454 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1208. Min Range: -8.1208
Max Act: 6.9645. Min Act: -0.1700
Data Index: 1406350 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1208. Min Range: -8.1208
Max Act: 6.9645. Min Act: -0.1700
Data Index: 1676082 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19